vmstats/vmevents flushing
Subsystems (5)
v3 cover vmstats/vmevents flushing
v3:
1) rearranged patches [2/3] and [3/3] to make [1/2] and [2/2] suitable for stable backporting
v2:
1) fixed !CONFIG_MEMCG_KMEM build by moving memcg_flush_percpu_vmstats() and memcg_flush_percpu_vmevents() out of CONFIG_MEMCG_KMEM
2) merged add-comments-to-slab-enums-definition patch in
Thanks!
Roman Gushchin (3):
mm: memcontrol: flush percpu vmstats before releasing memcg
mm: memcontrol: flush percpu vmevents before releasing memcg
mm: memcontrol: flush percpu slab vmstats on kmem offlining
include/linux/mmzone.h | 5 +-- mm/memcontrol.c | 79 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+), 2 deletions(-)
Signature · 1 line
2.21.0
PATCH v3 1/3 mm: memcontrol: flush percpu vmstats before releasing memcg
Percpu caching of local vmstats with the conditional propagation by the cgroup tree leads to an accumulation of errors on non-leaf levels.
Let's imagine two nested memory cgroups A and A/B. Say, a process belonging to A/B allocates 100 pagecache pages on the CPU 0. The percpu cache will spill 3 times, so that 32*3=96 pages will be accounted to A/B and A atomic vmstat counters, 4 pages will remain in the percpu cache.
Imagine A/B is nearby memory.max, so that every following allocation triggers a direct reclaim on the local CPU. Say, each such attempt will free 16 pages on a new cpu. That means every percpu cache will have -16 pages, except the first one, which will have 4 - 16 = -12. A/B and A atomic counters will not be touched at all.
Now a user removes A/B. All percpu caches are freed and corresponding vmstat numbers are forgotten. A has 96 pages more than expected.
As memory cgroups are created and destroyed, errors do accumulate. Even 1-2 pages differences can accumulate into large numbers.
To fix this issue let's accumulate and propagate percpu vmstat values before releasing the memory cgroup. At this point these numbers are stable and cannot be changed.
Since on cpu hotplug we do flush percpu vmstats anyway, we can iterate only over online cpus.
--- mm/memcontrol.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+)
mm/memcontrol.c +40 -0
@@ -3383,6 +3383,41 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } +static void memcg_flush_percpu_vmstats (struct mem_cgroup *memcg) +{ +unsigned long stat[MEMCG_NR_STAT ]; +struct mem_cgroup *mi; +int node, cpu, i; + +for (i =0 ; i <MEMCG_NR_STAT ; i++) + stat[i] =0 ; + +for_each_online_cpu (cpu) +for (i =0 ; i <MEMCG_NR_STAT ; i++) + stat[i] +=raw_cpu_read (memcg->vmstats_percpu->stat[i]); + +for (mi = memcg; mi; mi =parent_mem_cgroup (mi)) +for (i =0 ; i <MEMCG_NR_STAT ; i++) +atomic_long_add (stat[i], &mi->vmstats[i]); + +for_each_node (node) { +struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; +struct mem_cgroup_per_node *pi; + +for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) + stat[i] =0 ; + +for_each_online_cpu (cpu) +for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) + stat[i] +=raw_cpu_read ( + pn->lruvec_stat_cpu->count[i]); + +for (pi = pn; pi; pi =parent_nodeinfo (pi, node)) +for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) +atomic_long_add (stat[i], &pi->lruvec_stat[i]); + } +} +#ifdef CONFIG_MEMCG_KMEM static int memcg_online_kmem (struct mem_cgroup *memcg) {
@@ -4805,6 +4840,11 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) {int node; +/* +* Flush percpu vmstats to guarantee the value correctness +* on parent's and all ancestor levels. +*/ +memcg_flush_percpu_vmstats (memcg);for_each_node (node)free_mem_cgroup_per_node_info (memcg, node);free_percpu (memcg->vmstats_percpu);
Signature · 1 line
2.21.0
PATCH v3 2/3 mm: memcontrol: flush percpu vmevents before releasing memcg
In reply to Roman GushchinSimilar to vmstats, percpu caching of local vmevents leads to an accumulation of errors on non-leaf levels. This happens because some leftovers may remain in percpu caches, so that they are never propagated up by the cgroup tree and just disappear into nonexistence with on releasing of the memory cgroup.
To fix this issue let's accumulate and propagate percpu vmevents values before releasing the memory cgroup similar to what we're doing with vmstats.
Since on cpu hotplug we do flush percpu vmstats anyway, we can iterate only over online cpus.
--- mm/memcontrol.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-)
mm/memcontrol.c +21 -1
@@ -3418,6 +3418,25 @@ static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg) } } +static void memcg_flush_percpu_vmevents (struct mem_cgroup *memcg) +{ +unsigned long events[NR_VM_EVENT_ITEMS ]; +struct mem_cgroup *mi; +int cpu, i; + +for (i =0 ; i <NR_VM_EVENT_ITEMS ; i++) + events[i] =0 ; + +for_each_online_cpu (cpu) +for (i =0 ; i <NR_VM_EVENT_ITEMS ; i++) + events[i] +=raw_cpu_read ( + memcg->vmstats_percpu->events[i]); + +for (mi = memcg; mi; mi =parent_mem_cgroup (mi)) +for (i =0 ; i <NR_VM_EVENT_ITEMS ; i++) +atomic_long_add (events[i], &mi->vmevents[i]); +} +#ifdef CONFIG_MEMCG_KMEM static int memcg_online_kmem (struct mem_cgroup *memcg) {
@@ -4841,10 +4860,11 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)int node;/* -* Flush percpu vmstats to guarantee the value correctness +* Flush percpu vmstats and vmevents to guarantee the value correctness * on parent's and all ancestor levels. */ memcg_flush_percpu_vmstats (memcg); +memcg_flush_percpu_vmevents (memcg);for_each_node (node)free_mem_cgroup_per_node_info (memcg, node);free_percpu (memcg->vmstats_percpu);
Signature · 1 line
2.21.0
PATCH v3 3/3 mm: memcontrol: flush percpu slab vmstats on kmem offlining
In reply to Roman GushchinI've noticed that the "slab" value in memory.stat is sometimes 0, even if some children memory cgroups have a non-zero "slab" value. The following investigation showed that this is the result of the kmem_cache reparenting in combination with the per-cpu batching of slab vmstats.
At the offlining some vmstat value may leave in the percpu cache, not being propagated upwards by the cgroup hierarchy. It means that stats on ancestor levels are lower than actual. Later when slab pages are released, the precise number of pages is substracted on the parent level, making the value negative. We don't show negative values, 0 is printed instead.
To fix this issue, let's flush percpu slab memcg and lruvec stats on memcg offlining. This guarantees that numbers on all ancestor levels are accurate and match the actual number of outstanding slab pages.
--- include/linux/mmzone.h | 5 +++-- mm/memcontrol.c | 35 +++++++++++++++++++++++++++-------- 2 files changed, 30 insertions(+), 10 deletions(-)
include/linux/mmzone.h +3 -2
@@ -215,8 +215,9 @@ enum node_stat_item {NR_INACTIVE_FILE ,/* " " " " " */ NR_ACTIVE_FILE ,/* " " " " " */ NR_UNEVICTABLE ,/* " " " " " */ -NR_SLAB_RECLAIMABLE , -NR_SLAB_UNRECLAIMABLE , +NR_SLAB_RECLAIMABLE ,/* Please do not reorder this item */ +NR_SLAB_UNRECLAIMABLE ,/* and this one without looking at +* memcg_flush_percpu_vmstats() first. */ NR_ISOLATED_ANON ,/* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE ,/* Temporary isolated pages from file lru */ WORKINGSET_NODES,
mm/memcontrol.c +27 -8
@@ -3383,37 +3383,49 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } -static void memcg_flush_percpu_vmstats (struct mem_cgroup *memcg) +static void memcg_flush_percpu_vmstats (struct mem_cgroup *memcg,bool slab_only) {unsigned long stat[MEMCG_NR_STAT ];struct mem_cgroup *mi;int node, cpu, i; +int min_idx, max_idx; -for (i =0 ; i <MEMCG_NR_STAT ; i++) +if (slab_only) { + min_idx =NR_SLAB_RECLAIMABLE ; + max_idx =NR_SLAB_UNRECLAIMABLE ; + }else { + min_idx =0 ; + max_idx =MEMCG_NR_STAT ; + } + +for (i = min_idx; i < max_idx; i++) stat[i] =0 ;for_each_online_cpu (cpu) -for (i =0 ; i <MEMCG_NR_STAT ; i++) +for (i = min_idx; i < max_idx; i++) stat[i] +=raw_cpu_read (memcg->vmstats_percpu->stat[i]);for (mi = memcg; mi; mi =parent_mem_cgroup (mi)) -for (i =0 ; i <MEMCG_NR_STAT ; i++) +for (i = min_idx; i < max_idx; i++)atomic_long_add (stat[i], &mi->vmstats[i]); +if (!slab_only) + max_idx =NR_VM_NODE_STAT_ITEMS ; +for_each_node (node) {struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];struct mem_cgroup_per_node *pi; -for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) +for (i = min_idx; i < max_idx; i++) stat[i] =0 ;for_each_online_cpu (cpu) -for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) +for (i = min_idx; i < max_idx; i++) stat[i] +=raw_cpu_read ( pn->lruvec_stat_cpu->count[i]);for (pi = pn; pi; pi =parent_nodeinfo (pi, node)) -for (i =0 ; i <NR_VM_NODE_STAT_ITEMS ; i++) +for (i = min_idx; i < max_idx; i++)atomic_long_add (stat[i], &pi->lruvec_stat[i]); } }
@@ -3486,7 +3498,14 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)if (!parent) parent = root_mem_cgroup; +/* +* Deactivate and reparent kmem_caches. Then flush percpu +* slab statistics to have precise values at the parent and +* all ancestor levels. It's required to keep slab stats +* accurate after the reparenting of kmem_caches. +*/ memcg_deactivate_kmem_caches (memcg, parent); +memcg_flush_percpu_vmstats (memcg, true); kmemcg_id = memcg->kmemcg_id;BUG_ON (kmemcg_id <0 );
@@ -4863,7 +4882,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)* Flush percpu vmstats and vmevents to guarantee the value correctness * on parent's and all ancestor levels. */ -memcg_flush_percpu_vmstats (memcg); +memcg_flush_percpu_vmstats (memcg, false);memcg_flush_percpu_vmevents (memcg);for_each_node (node)free_mem_cgroup_per_node_info (memcg, node);
Signature · 1 line
2.21.0
Andrew Morton
maintainerQuoted 9 lines · On Mon, 19 Aug 2019 16:00:51 -0700 Roman Gushchin <[email protected]> wrote:
v3:
1) rearranged patches [2/3] and [3/3] to make [1/2] and [2/2] suitable for stable backportingv2:
1) fixed !CONFIG_MEMCG_KMEM build by movingmemcg_flush_percpu_vmstats()andmemcg_flush_percpu_vmevents()out ofCONFIG_MEMCG_KMEM
2) merged add-comments-to-slab-enums-definition patch in
Quoted 7 lines
Thanks!
Roman Gushchin (3):
mm: memcontrol: flush percpu vmstats before releasing memcg
mm: memcontrol: flush percpu vmevents before releasing memcg
mm: memcontrol: flush percpu slab vmstats on kmem offlining
Can you please explain why the first two patches were cc:stable but not the third?
Quoted 13 lines · Andrew Morton
Quoted 11 lines · On Mon, 19 Aug 2019 16:00:51 -0700 Roman Gushchin <[email protected]> wrote:
v3:
1) rearranged patches [2/3] and [3/3] to make [1/2] and [2/2] suitable for stable backportingv2:
1) fixed !CONFIG_MEMCG_KMEM build by movingmemcg_flush_percpu_vmstats()andmemcg_flush_percpu_vmevents()out ofCONFIG_MEMCG_KMEM
2) merged add-comments-to-slab-enums-definition patch inThanks!
Quoted 10 lines
Quoted 5 lines
Roman Gushchin (3):
mm: memcontrol: flush percpu vmstats before releasing memcg
mm: memcontrol: flush percpu vmevents before releasing memcg
mm: memcontrol: flush percpu slab vmstats on kmem offliningCan you please explain why the first two patches were cc:stable but not the third?
Because [1] and [2] are fixing commit 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty"), which has been merged into 5.2.
And [3] fixes commit fb2f2b0adb98 ("mm: memcg/slab: reparent memcg kmem_caches on cgroup removal"), which is in not yet released 5.3, so stable backport isn't required.
Thanks!
Andrew Morton
maintainerQuoted 25 lines · On Fri, 23 Aug 2019 00:33:51 +0000 Roman Gushchin <[email protected]> wrote:
Quoted 13 lines · Andrew Morton
Quoted 11 lines · On Mon, 19 Aug 2019 16:00:51 -0700 Roman Gushchin <[email protected]> wrote:
v3:
1) rearranged patches [2/3] and [3/3] to make [1/2] and [2/2] suitable for stable backportingv2:
1) fixed !CONFIG_MEMCG_KMEM build by movingmemcg_flush_percpu_vmstats()andmemcg_flush_percpu_vmevents()out ofCONFIG_MEMCG_KMEM
2) merged add-comments-to-slab-enums-definition patch inThanks!
Quoted 10 lines
Quoted 5 lines
Roman Gushchin (3):
mm: memcontrol: flush percpu vmstats before releasing memcg
mm: memcontrol: flush percpu vmevents before releasing memcg
mm: memcontrol: flush percpu slab vmstats on kmem offliningCan you please explain why the first two patches were cc:stable but not the third?
Quoted 6 lines
Because [1] and [2] are fixing commit
42a300353577("mm: memcontrol: fix recursive statistics correctness & scalabilty"), which has been merged into 5.2.And [3] fixes commit
fb2f2b0adb98("mm: memcg/slab: reparent memcgkmem_cacheson cgroup removal"), which is in not yet released 5.3, so stable backport isn't required.
OK, thanks. Patches 1 & 2 are good to go but I don't think that #3 has had suitable review and I have a note here that Michal has concerns with it.
Michal Hocko
maintainerQuoted 30 lines · Andrew Morton
Quoted 28 lines · On Fri, 23 Aug 2019 00:33:51 +0000 Roman Gushchin <[email protected]> wrote:
Quoted 13 lines · Andrew Morton
Quoted 11 lines · On Mon, 19 Aug 2019 16:00:51 -0700 Roman Gushchin <[email protected]> wrote:
v3:
1) rearranged patches [2/3] and [3/3] to make [1/2] and [2/2] suitable for stable backportingv2:
1) fixed !CONFIG_MEMCG_KMEM build by movingmemcg_flush_percpu_vmstats()andmemcg_flush_percpu_vmevents()out ofCONFIG_MEMCG_KMEM
2) merged add-comments-to-slab-enums-definition patch inThanks!
Quoted 10 lines
Quoted 5 lines
Roman Gushchin (3):
mm: memcontrol: flush percpu vmstats before releasing memcg
mm: memcontrol: flush percpu vmevents before releasing memcg
mm: memcontrol: flush percpu slab vmstats on kmem offliningCan you please explain why the first two patches were cc:stable but not the third?
Because [1] and [2] are fixing commit
42a300353577("mm: memcontrol: fix recursive statistics correctness & scalabilty"), which has been merged into 5.2.
Quoted 7 lines
Quoted 3 lines
And [3] fixes commit
fb2f2b0adb98("mm: memcg/slab: reparent memcgkmem_cacheson cgroup removal"), which is in not yet released 5.3, so stable backport isn't required.OK, thanks. Patches 1 & 2 are good to go but I don't think that #3 has had suitable review and I have a note here that Michal has concerns with it.
My concern was http://lkml.kernel.org/r/[email protected]
so more of a code style kinda thing. Roman has chosen to stay with his original form and added a comment that NR_SLAB_{UN}RECLAIMABLE are magic. This is something I can live with even though I would have preferred it a different way. Nothing serious enough to Nack or insist.
Signature · 2 lines
Michal Hocko SUSE Labs